Research map / Image generation / Image restoration
SinDDM: A Single Image Denoising Diffusion Model
Vladimir Kulikov, Shahar Yadin, Matan Kleiner, Tomer Michaeli
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace GAN pyramid with multi-scale diffusion denoiser (SinDDM) | single-image unconditional generation · Single-image unconditional generation (12 images) | Pixel Div. and LPIPS Div.: Pixel 0.32 vs 0.28 best baseline; LPIPS 0.21 vs 0.18 | Improved |
| Replace GAN pyramid with multi-scale diffusion denoiser (SinDDM) | single-image unconditional generation · Single-image unconditional generation (12 images) | SIFID: 0.34 vs 0.05 for GPNN (best) | Hurt |
| Replace GAN pyramid with multi-scale diffusion denoiser (SinDDM) | single-image unconditional generation · Single-image unconditional generation (12 images) | NIQE/NIMA/MUSIQ: comparable quality; NIMA 5.8 best, MUSIQ 48 below GPNN 52.8 | No clear effect |
| Train with blur added to multi-scale pyramid (vs no blur) (ablation) | SinDDM · Qualitative, training image examples | fine detail preservation | Improved |
| Add CLIP momentum update (lambda=0.05) to text guidance | SinDDM text-guided generation · Text-guided generation | guidance effectiveness | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SinGAN — SinGAN: Learning a Generative Model From a Single Natural Image (ICCV 2019) · better on 5 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Denoising Diffusion Bridge Models (ICLR 2024 · similarity 0.92)
- UDPM: Upsampling Diffusion Probabilistic Models (NeurIPS 2024 · similarity 0.91)
- Directly Denoising Diffusion Models (ICML 2024 · similarity 0.91)
- Residual Denoising Diffusion Models (CVPR 2024 · similarity 0.90)
- Diffusion Bridge Implicit Models (ICLR 2025 · similarity 0.90)
- Diffusion Models Without Attention (CVPR 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
